hw/nvme: Use ioeventfd to handle doorbell updates

Add property "ioeventfd" which is enabled by default. When this is
enabled, updates on the doorbell registers will cause KVM to signal
an event to the QEMU main loop to handle the doorbell updates.
Therefore, instead of letting the vcpu thread run both guest VM and
IO emulation, we now use the main loop thread to do IO emulation and
thus the vcpu thread has more cycles for the guest VM.

Since ioeventfd does not tell us the exact value that is written, it is
only useful when shadow doorbell buffer is enabled, where we check
for the value in the shadow doorbell buffer when we get the doorbell
update event.

IOPS comparison on Linux 5.19-rc2: (Unit: KIOPS)

qd           1   4  16  64
qemu        35 121 176 153
ioeventfd   41 133 258 313

Changes since v3:
 - Do not deregister ioeventfd when it was not enabled on a SQ/CQ

Signed-off-by: Jinhao Fan <fanjinhao21s@ict.ac.cn>
Reviewed-by: Klaus Jensen <k.jensen@samsung.com>
Signed-off-by: Klaus Jensen <k.jensen@samsung.com>

1 files changed, 5 insertions, 0 deletions

diff --git a/hw/nvme/nvme.h b/hw/nvme/nvme.h
index 0711b97..79f5c28 100644
--- a/hw/nvme/nvme.h
+++ b/hw/nvme/nvme.h
@@ -376,6 +376,8 @@ typedef struct NvmeSQueue {
     uint64_t    db_addr;
     uint64_t    ei_addr;
     QEMUTimer   *timer;
+    EventNotifier notifier;
+    bool        ioeventfd_enabled;
     NvmeRequest *io_req;
     QTAILQ_HEAD(, NvmeRequest) req_list;
     QTAILQ_HEAD(, NvmeRequest) out_req_list;
@@ -395,6 +397,8 @@ typedef struct NvmeCQueue {
     uint64_t    db_addr;
     uint64_t    ei_addr;
     QEMUTimer   *timer;
+    EventNotifier notifier;
+    bool        ioeventfd_enabled;
     QTAILQ_HEAD(, NvmeSQueue) sq_list;
     QTAILQ_HEAD(, NvmeRequest) req_list;
 } NvmeCQueue;
@@ -417,6 +421,7 @@ typedef struct NvmeParams {
     uint8_t  zasl;
     bool     auto_transition_zones;
     bool     legacy_cmb;
+    bool     ioeventfd;
     uint8_t  sriov_max_vfs;
     uint16_t sriov_vq_flexible;
     uint16_t sriov_vi_flexible;